┌─────────────────────────────────────────────┐
│ Single Server (64GB RAM, no GPU) │
│ │
│ 🎛️ Controller │
│ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ │
│ │Alice │ │Bob │ │Carol │ │...×24│ │
│ │Mktg │ │Ops │ │Fin │ │ │ │
│ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ │
│ └─────────┴─────────┴────────┘ │
│ Shared knowledge + team memory │
└─────────────────────────────────────────────┘
┌─────────────────────────────────────────────┐
│ Single Server (64GB RAM, no GPU) │
│ │
│ 🎛️ Controller │
│ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ │
│ │Alice │ │Bob │ │Carol │ │...×24│ │
│ │Mktg │ │Ops │ │Fin │ │ │ │
│ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ │
│ └─────────┴─────────┴────────┘ │
│ Shared knowledge + team memory │
└─────────────────────────────────────────────┘
┌─────────────────────────────────────────────┐
│ Single Server (64GB RAM, no GPU) │
│ │
│ 🎛️ Controller │
│ ┌──────┐ ┌──────┐ ┌──────┐ ┌──────┐ │
│ │Alice │ │Bob │ │Carol │ │...×24│ │
│ │Mktg │ │Ops │ │Fin │ │ │ │
│ └──┬───┘ └──┬───┘ └──┬───┘ └──┬───┘ │
│ └─────────┴─────────┴────────┘ │
│ Shared knowledge + team memory │
└─────────────────────────────────────────────┘ - Private memory: Conversation history persists locally.
- Shared context: Read-only access to a company Knowledge Base.
- Interface: Slack channels are the primary UI.
- Tasking: Connected to Notion for structured input/output. - Personal (per agent): Capped at 5KB. Auto-pruned weekly.
- Member (per human): Correction history and preferences for each team member the agent works with.
- Channel (per topic): Indexed with embeddings for semantic search.
- Company (shared): Vetted knowledge that never expires. - Agent records locally in .learnings/corrections.md.
- Same correction happens twice → promote to the agent's "Core Rules."
- Applies fleet-wide → promote to shared rules.
- Contradictions are flagged for a human to resolve. - Goals have explicit dependencies.
- Agents must declare what they're blocked on.
- The controller monitors for stalls (no progress log in 24h → escalate).
- P2P handoffs have timeouts. - Moved to on-demand loading of shared knowledge.
- Built a semantic search tool (we call it Teamind) instead of context stuffing. Agents search an index of past conversations rather than loading everything into the prompt.
- Pruned system prompts to essentials (<2K tokens). - Auto-execute: Low-risk, reversible.
- Notify-and-proceed: Medium-risk, human gets a ping.
- Wait-for-approval: High-risk, blocks until human clicks "Yes." - A team that already uses AI assistants.
- Repetitive coordination overhead you want to eliminate.
- A high tolerance for debugging agents that misunderstand each other.
